4FGL Results
SH
Note that the R library keras conflicts with other R libraries. Better remove other unnecessary R packages for this script.
Other links
This is Script 4.
Script 3: Classification on 4FGL2 (Part2) here.
Script 2: Classification on 4FGL2 (Part1) here.
Script 1: Comparing FGL3 unclassified predictions and FGL4 discoveries. See here.
Script 0: Data pre-processing. FGL4_tidy_for_FGL3.rData" are processed 4FGL data catalog. See the processing (and preliminary feature selection via correlation) steps here.
load("fermicatsR/FGL4_results.rData")
load("fermicatsR/FGL4_tidy.rData")
load("fermicatsR/FGL4_tidy_for_FGL3.rData")
library(devtools)
library(dplyr)
FGL4_unassoc_results <- FGL4_results %>%
filter(CLASS1 == "" & CLASS2== "") %>%
filter(Signif > 4) %>% #4: 1008 obs
# filter(LR_Pred==RF_Pred) %>% #4: 921 obs
# filter(LR_Pred=="PSR") %>%
arrange(desc(Signif)) 4FGL Unassociated Sources Prediction Results
library(DT)
DT::datatable(FGL4_unassoc_results)4FGL Whole Catalog Prediction Results
DT::datatable(FGL4_results)## Warning in instance$preRenderHook(instance): It seems your data is too big
## for client-side DataTables. You may consider server-side processing: https://
## rstudio.github.io/DT/server.html
